- removed old tests

- ported all custom filters and using python std implemetation for ascii and bin filters
This commit is contained in:
ari committed 2020-10-20 19:24:15 -04:00
1 parent 5fd03d1250
commit 4d1e0f2389
19 files changed
+831 -216

No files matched your search

+24
View File
@@ -0,0 +1,24 @@
from pathlib import Path
from unittest import TestCase, main
from pdfmajor.interpreter import PDFInterpreter
from pdfmajor.execptions import UnicodeNotDefined
CURRENT_FOLDER = Path("./")
class BadUnicode(TestCase):
def test_ensure_failure(self):
pdf = PDFInterpreter(CURRENT_FOLDER / "tests" / "samples" / "pdf" / "bad-unicode.pdf", ignore_bad_chars=False)
pages = list(pdf)
with self.assertRaises(UnicodeNotDefined):
list(pages[2])
def test_ensure_no_failure(self):
pdf = PDFInterpreter(CURRENT_FOLDER / "tests" / "samples" / "pdf" / "bad-unicode.pdf", ignore_bad_chars=True)
pages = list(pdf)
list(pages[2])
if __name__ == '__main__':
# Run Tests
main()
+38
View File
@@ -0,0 +1,38 @@
import os
from unittest import TestCase, main
# from pdfmajor.extractor import extract_items_from_pdf
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter.commands import LTContainer
CUR_PATH = os.path.dirname(os.path.dirname(__file__))
INPUT_FOLDER = os.path.join(
CUR_PATH, "tests/samples/pdf"
)
FILES = os.listdir(INPUT_FOLDER)
NUM_LOOPS = 10
def count_elms(file_path: str):
count = 0
for page in PDFInterpreter(file_path, ignore_bad_chars=True):
for item in page:
if isinstance(item, LTContainer):
count += len([*item])
else:
count += 1
return count
class CachingTester(TestCase):
def test_cache(self):
for file_name in FILES:
self.subTest(name = file_name)
file_path = os.path.join(INPUT_FOLDER, file_name)
last_count = count_elms(file_path)
for _ in range(NUM_LOOPS):
new_count = count_elms(file_path)
self.assertEqual( new_count , last_count )
last_count = new_count
if __name__ == '__main__':
# Run Tests
main()
+115
View File
@@ -0,0 +1,115 @@
import os
from typing import List
from unittest import TestCase, main
# from pdfmajor.extractor import extract_items_from_pdf
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter.commands import LTCurve, PDFColor, LTXObject
from pdfmajor.interpreter.commands import PREDEFINED_COLORSPACE
CUR_PATH = os.path.dirname(os.path.dirname(__file__))
INPUT_FOLDER = os.path.join(
CUR_PATH, "tests/samples/pdf"
)
FILES = os.listdir(INPUT_FOLDER)
NUM_LOOPS = 10
class ColorTest(TestCase):
def run_test(self, file_path: str, curve_defs: List[List[PDFColor]]):
def run_once(item):
if isinstance(item, LTCurve):
t_stroke, t_fill = curve_defs.pop(0)
self.assertEqual( item.stroke.values, t_stroke.values )
self.assertEqual( item.stroke.color_space, t_stroke.color_space )
self.assertEqual( item.fill.values, t_fill.values )
self.assertEqual( item.fill.color_space, t_fill.color_space )
elif isinstance(item, LTXObject):
for c in item:
run_once(c)
for page in PDFInterpreter(file_path):
for item in page:
run_once(item)
def test_lorem_v3(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v3.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 0),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 0),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 0, 0),
]
] +
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
]]*24)+
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 0),
]]*11)+
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 128, 128, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 0),
]]*5)+
[[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
]]
)
def test_lorem_v4(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v4.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 64, 64, 64),
]
]
)
def test_lorem_v5(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v5.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 128, 128, 128),
]
]
)
if __name__ == '__main__':
# Run Tests
main()
+61
View File
@@ -0,0 +1,61 @@
#!/usr/bin/env python
import re
import os
import logging
from unittest import TestCase, main
from typing import List
from pdfmajor.converters import convert_file
from xml.etree import ElementTree
from json import load as json_load
from tqdm import tqdm
def rel_path(*arg: str) -> str:
return os.path.normpath(os.path.join(os.path.dirname(__file__), *arg))
EXTS = ['text', 'json','xml','html']
INPUT_FOLDER = rel_path("./samples/pdf")
OUTPUT_FOLDER = rel_path(f"./samples/output/")
if not os.path.exists(OUTPUT_FOLDER):
os.makedirs(OUTPUT_FOLDER)
files = os.listdir(INPUT_FOLDER)
TOTAL = len(files)*len(EXTS)
class ConversionTest(TestCase):
def test_conversion(self):
# with tqdm(total=TOTAL) as waiter:
for idx, file_name in enumerate(files):
self.subTest(i=idx);
file_name_no_ext = re.sub(r'\.pdf$',"", file_name)
input_file_path = os.path.join(INPUT_FOLDER, file_name)
for ext in EXTS:
if not os.path.exists(os.path.join(OUTPUT_FOLDER, ext)):
os.makedirs(os.path.join(OUTPUT_FOLDER, ext))
output_file_path = os.path.join(OUTPUT_FOLDER, ext, file_name_no_ext + "." + ext)
if len(file_name) > len(file_name_no_ext):
# waiter.set_description(f"Conversion test -- {file_name}")
convert_file(
input_file=input_file_path,
output_file=output_file_path,
out_type=ext,
ignore_bad_chars=True,
debug_level=logging.WARN,
)
if ext == 'xml':
# waiter.set_description(f" > testing format {file_name}")
ElementTree.parse(output_file_path)
elif ext == 'json':
# waiter.set_description(f" > testing format {file_name}")
with open(output_file_path, 'r') as outf:
json_load(outf)
# waiter.update()
# waiter.set_description("Done")
if __name__ == '__main__':
# Run Tests
main()
+82
View File
@@ -0,0 +1,82 @@
from contextlib import contextmanager
from unittest import TestCase, main
from typing import List, Tuple, Callable
from os import remove
from tempfile import mktemp
from pdfmajor.converters.writers.html import HTMLMaker
from tqdm import tqdm
# Make temp file
FILE_NAME = mktemp()
TestFunction = Callable[[HTMLMaker], str];
TESTS: List[Tuple[TestFunction, str]] = [];
class HTMLTester(TestCase):
@contextmanager
def get_html(self):
with HTMLMaker(FILE_NAME) as html:
yield html
def compare(self, expected: str):
with open(FILE_NAME, 'r') as f:
self.assertEqual(f.read() , expected)
def test_html_basic(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
html.write("test")
self.compare("""<html >
test
</html>""")
def test_html_with_attributes(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
self.compare("""<html >
<head >
<meta http-equiv="Content-Type" content="text/html" />
</head>
</html>""")
def test_html_with_children(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
with html.elm("body"):
with html.elm("h1", css={"color": "red"}):
html.write("Hello World")
self.compare("""<html >
<head >
<meta http-equiv="Content-Type" content="text/html" />
</head>
<body >
<h1 style="color: red">
Hello World
</h1>
</body>
</html>""")
def test_html_with_css(self):
with self.get_html() as html:
with html.elm('style'):
html.write('''.page { position: relative; overflow: hidden;border: 1px black solid;}''')
self.compare("""<style >
.page { position: relative; overflow: hidden;border: 1px black solid;}
</style>
""")
if __name__ == '__main__':
# Run Tests
main()
# Clean up
remove(FILE_NAME)
+41
View File
@@ -0,0 +1,41 @@
import os
from unittest import TestCase, main
from pdfmajor.interpreter import LTImage, logging
from pdfmajor.interpreter import PageInterpreter, PDFInterpreter
from pdfmajor.interpreter.commands import LTItem
from pdfmajor.interpreter.commands import LTCharBlock, LTChar
CUR_PATH = os.path.dirname(os.path.dirname(__file__))
FILES = [
"jpg",
"looseless"
]
OUTPUT_FOLDER = os.path.join(
CUR_PATH,
'samples/output/images'
)
if not os.path.exists(OUTPUT_FOLDER):
os.makedirs(OUTPUT_FOLDER)
class ImageTester(TestCase):
def test_image_extract(self):
for file_name in FILES:
self.subTest(file_name=file_name)
for page in PDFInterpreter(os.path.join(
CUR_PATH,
f"tests/samples/pdf/{file_name}.pdf"
), debug_level=logging.ERROR):
self.assertTrue( isinstance(page, PageInterpreter) )
for item_idx, item in enumerate(page):
self.assertTrue( isinstance(item, LTItem) )
if isinstance(item, LTImage):
item.save_image(
OUTPUT_FOLDER,
file_name=f'{file_name}_p{page.page_num}i{item_idx}'
)
if __name__ == '__main__':
# Run Tests
main()
+29
View File
@@ -0,0 +1,29 @@
import os
from unittest import TestCase, main
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter.commands import LTItem
from pdfmajor.interpreter.commands import LTCharBlock, LTChar
CUR_PATH = os.path.dirname(os.path.dirname(__file__))
INPUT_FOLDER = os.path.join(
CUR_PATH, "tests/samples/pdf"
)
FILES = os.listdir(INPUT_FOLDER)
class TestInterpreter(TestCase):
def test_pdfintp(self):
for file_name in FILES:
self.subTest(file_name=file_name)
file_path = os.path.join(INPUT_FOLDER, file_name)
for page in PDFInterpreter(file_path, debug_level=logging.ERROR, ignore_bad_chars=True):
self.assertTrue( isinstance(page, PageInterpreter) )
for item in page:
self.assertTrue( isinstance(item, LTItem) )
if isinstance(item, LTCharBlock):
for char in item:
self.assertTrue( isinstance(char, LTChar) )
if __name__ == '__main__':
# Run Tests
main()
+111
View File
@@ -0,0 +1,111 @@
from os import remove
from tempfile import mktemp
from pdfmajor.converters.writers.json import JSONMaker
# Make temp file
FILE_NAME = mktemp()
with JSONMaker(FILE_NAME) as obj:
obj.number("a", 2)
obj.string("hello", "world")
assert(open(FILE_NAME, 'r').read() == """{
"a": 2,
"hello": "world"
}""")
with JSONMaker(FILE_NAME) as obj:
with obj.object("test") as child:
child.number("A", 2)
assert(open(FILE_NAME, 'r').read() == """{
"test": {
"A": 2
}
}""")
with JSONMaker(FILE_NAME) as obj:
with obj.object("hello") as child:
with child.object("nested") as nested:
with nested.object("so") as so:
so.string("really", 'nested'),
so.number("man", 2)
nested.number("he", 3)
child.string('fo', 'real')
obj.string('fo', 'real2')
assert(open(FILE_NAME, 'r').read() == """{
"hello": {
"nested": {
"so": {
"really": "nested",
"man": 2
},
"he": 3
},
"fo": "real"
},
"fo": "real2"
}""")
with JSONMaker(FILE_NAME) as obj:
with obj.array("hello") as child:
child.number(1)
with child.array() as nchild:
nchild.string('wow')
child.number(3)
assert(open(FILE_NAME, 'r').read() == """{
"hello": [
1,
[
"wow"
],
3
]
}""")
with JSONMaker(FILE_NAME) as obj:
with obj.array("pages") as pages:
with pages.object() as page:
page.number("id", 1)
page.number("height", 20)
page.number("width", 20)
with page.array("children") as children:
with children.object() as item:
item.string("type", "char-block")
item.string("text", "test")
item.string("color_type", "rgb")
with item.array("color_vals") as col_vals:
col_vals.number(0)
col_vals.number(0)
col_vals.number(0)
item.number("x0", 2)
item.number("x1", 4.2)
item.number("y0", 231.12)
item.number("y1", 331.12)
assert(open(FILE_NAME, 'r').read() == """{
"pages": [
{
"id": 1,
"height": 20,
"width": 20,
"children": [
{
"type": "char-block",
"text": "test",
"color_type": "rgb",
"color_vals": [
0,
0,
0
],
"x0": 2,
"x1": 4.2,
"y0": 231.12,
"y1": 331.12
}
]
}
]
}""")
# Clean up
remove(FILE_NAME)
+101
View File
@@ -0,0 +1,101 @@
from os import remove
from tempfile import mktemp
from pdfmajor.converters.writers.yaml import YAMLMaker
# Make temp file
FILE_NAME = mktemp()
with YAMLMaker(FILE_NAME) as yml:
yml.write("name", "bob")
yml.write("age", "20")
with yml.object("wife") as wife:
wife.write("name", "kory")
wife.write("age", "21")
with yml.array("children") as children:
with children.object() as child:
child.write("name", "Mike")
with child.array("toys") as toys:
toys.write("lion")
toys.write("bear")
with yml.object("computer") as computer:
computer.write("type", "awesome")
assert(open(FILE_NAME, 'r').read() == """name: bob
age: 20
wife:
name: kory
age: 21
children:
- name: Mike
toys:
- lion
- bear
computer:
type: awesome""")
with YAMLMaker(FILE_NAME) as yml:
yml.write("name", "bob")
yml.write("age", "20")
yml.place_object("wife", {
"name": "kory",
"age": 21
})
with yml.array("children") as children:
with children.object() as child:
child.write("name", "Mike")
child.place_array("toys", [
"lion", "bear"
])
yml.place_object("computer", {"type": "awesome"})
assert(open(FILE_NAME, 'r').read() == """name: bob
age: 20
wife:
name: kory
age: 21
children:
- name: Mike
toys:
- lion
- bear
computer:
type: awesome""")
with YAMLMaker(FILE_NAME) as yml:
with yml.array('pages') as pages:
with pages.object() as page:
page.write("id", 0)
page.write("width", 100)
page.write("height", 200)
with page.array("children") as children:
with children.object() as curve:
with curve.object("stroke") as fill:
fill.write("type", "DeviceRGB")
fill.write("value", ['1','2','3'])
curve.write("x0", 0)
curve.write("x1", 1)
with curve.object("fill") as fill:
fill.write("type", "DeviceRGB")
fill.write("value", ['1','2','3'])
curve.write("y0", 0)
curve.write("y1", 1)
assert(open(FILE_NAME, 'r').read() == """pages:
- id: 0
width: 100
height: 200
children:
- stroke:
type: DeviceRGB
value: ['1', '2', '3']
x0: 0
x1: 1
fill:
type: DeviceRGB
value: ['1', '2', '3']
y0: 0
y1: 1""")
# Clean up
remove(FILE_NAME)